Ayan Kumar Bhunia

Pinaki Nath Chowdhury, Aneeshan Sain, Ayan Kumar Bhunia et al.

We advance sketch research to scenes with the first dataset of freehand scene sketches, FS-COCO. With practical applications in mind, we collect sketches that convey scene content well but can be sketched within a few minutes by a person with any sketching skills. Our dataset comprises 10,000 freehand scene vector sketches with per point space-time information by 100 non-expert individuals, offering both object- and scene-level abstraction. Each sketch is augmented with its text description. Using our dataset, we study for the first time the problem of fine-grained image retrieval from freehand scene sketches and sketch captions. We draw insights on: (i) Scene salience encoded in sketches using the strokes temporal order; (ii) Performance comparison of image retrieval from a scene sketch and an image caption; (iii) Complementarity of information in sketches and image captions, as well as the potential benefit of combining the two modalities. In addition, we extend a popular vector sketch LSTM-based encoder to handle sketches with larger complexity than was supported by previous work. Namely, we propose a hierarchical sketch decoder, which we leverage at a sketch-specific "pre-text" task. Our dataset enables for the first time research on freehand scene sketch understanding and its practical applications.

Pinaki Nath Chowdhury, Ayan Kumar Bhunia, Viswanatha Reddy Gajjala et al.

We scrutinise an important observation plaguing scene-level sketch research -- that a significant portion of scene sketches are "partial". A quick pilot study reveals: (i) a scene sketch does not necessarily contain all objects in the corresponding photo, due to the subjective holistic interpretation of scenes, (ii) there exists significant empty (white) regions as a result of object-level abstraction, and as a result, (iii) existing scene-level fine-grained sketch-based image retrieval methods collapse as scene sketches become more partial. To solve this "partial" problem, we advocate for a simple set-based approach using optimal transport (OT) to model cross-modal region associativity in a partially-aware fashion. Importantly, we improve upon OT to further account for holistic partialness by comparing intra-modal adjacency matrices. Our proposed method is not only robust to partial scene-sketches but also yields state-of-the-art performance on existing datasets.

Subhadeep Koley, Ayan Kumar Bhunia, Aneeshan Sain et al.

Given an abstract, deformed, ordinary sketch from untrained amateurs like you and me, this paper turns it into a photorealistic image - just like those shown in Fig. 1(a), all non-cherry-picked. We differ significantly from prior art in that we do not dictate an edgemap-like sketch to start with, but aim to work with abstract free-hand human sketches. In doing so, we essentially democratise the sketch-to-photo pipeline, "picturing" a sketch regardless of how good you sketch. Our contribution at the outset is a decoupled encoder-decoder training paradigm, where the decoder is a StyleGAN trained on photos only. This importantly ensures that generated results are always photorealistic. The rest is then all centred around how best to deal with the abstraction gap between sketch and photo. For that, we propose an autoregressive sketch mapper trained on sketch-photo pairs that maps a sketch to the StyleGAN latent space. We further introduce specific designs to tackle the abstract nature of human sketches, including a fine-grained discriminative loss on the back of a trained sketch-photo retrieval model, and a partial-aware sketch augmentation strategy. Finally, we showcase a few downstream tasks our generation model enables, amongst them is showing how fine-grained sketch-based image retrieval, a well-studied problem in the sketch community, can be reduced to an image (generated) to image retrieval task, surpassing state-of-the-arts. We put forward generated results in the supplementary for everyone to scrutinise.

Ayan Kumar Bhunia, Subhadeep Koley, Abdullah Faiz Ur Rahman Khilji et al.

Sketching enables many exciting applications, notably, image retrieval. The fear-to-sketch problem (i.e., "I can't sketch") has however proven to be fatal for its widespread adoption. This paper tackles this "fear" head on, and for the first time, proposes an auxiliary module for existing retrieval models that predominantly lets the users sketch without having to worry. We first conducted a pilot study that revealed the secret lies in the existence of noisy strokes, but not so much of the "I can't sketch". We consequently design a stroke subset selector that {detects noisy strokes, leaving only those} which make a positive contribution towards successful retrieval. Our Reinforcement Learning based formulation quantifies the importance of each stroke present in a given subset, based on the extent to which that stroke contributes to retrieval. When combined with pre-trained retrieval models as a pre-processing module, we achieve a significant gain of 8%-10% over standard baselines and in turn report new state-of-the-art performance. Last but not least, we demonstrate the selector once trained, can also be used in a plug-and-play manner to empower various sketch applications in ways that were not previously possible.

Pinaki Nath Chowdhury, Ayan Kumar Bhunia, Aneeshan Sain et al.

Sketches are highly expressive, inherently capturing subjective and fine-grained visual cues. The exploration of such innate properties of human sketches has, however, been limited to that of image retrieval. In this paper, for the first time, we cultivate the expressiveness of sketches but for the fundamental vision task of object detection. The end result is a sketch-enabled object detection framework that detects based on what \textit{you} sketch -- \textit{that} ``zebra'' (e.g., one that is eating the grass) in a herd of zebras (instance-aware detection), and only the \textit{part} (e.g., ``head" of a ``zebra") that you desire (part-aware detection). We further dictate that our model works without (i) knowing which category to expect at testing (zero-shot) and (ii) not requiring additional bounding boxes (as per fully supervised) and class labels (as per weakly supervised). Instead of devising a model from the ground up, we show an intuitive synergy between foundation models (e.g., CLIP) and existing sketch models build for sketch-based image retrieval (SBIR), which can already elegantly solve the task -- CLIP to provide model generalisation, and SBIR to bridge the (sketch$\rightarrow$photo) gap. In particular, we first perform independent prompting on both sketch and photo branches of an SBIR model to build highly generalisable sketch and photo encoders on the back of the generalisation ability of CLIP. We then devise a training paradigm to adapt the learned encoders for object detection, such that the region embeddings of detected boxes are aligned with the sketch and photo embeddings from SBIR. Evaluating our framework on standard object detection datasets like PASCAL-VOC and MS-COCO outperforms both supervised (SOD) and weakly-supervised object detectors (WSOD) on zero-shot setups. Project Page: \url{https://pinakinathc.github.io/sketch-detect}

Pinaki Nath Chowdhury, Ayan Kumar Bhunia, Aneeshan Sain et al.

In this paper, we extend scene understanding to include that of human sketch. The result is a complete trilogy of scene representation from three diverse and complementary modalities -- sketch, photo, and text. Instead of learning a rigid three-way embedding and be done with it, we focus on learning a flexible joint embedding that fully supports the ``optionality" that this complementarity brings. Our embedding supports optionality on two axes: (i) optionality across modalities -- use any combination of modalities as query for downstream tasks like retrieval, (ii) optionality across tasks -- simultaneously utilising the embedding for either discriminative (e.g., retrieval) or generative tasks (e.g., captioning). This provides flexibility to end-users by exploiting the best of each modality, therefore serving the very purpose behind our proposal of a trilogy in the first place. First, a combination of information-bottleneck and conditional invertible neural networks disentangle the modality-specific component from modality-agnostic in sketch, photo, and text. Second, the modality-agnostic instances from sketch, photo, and text are synergised using a modified cross-attention. Once learned, we show our embedding can accommodate a multi-facet of scene-related tasks, including those enabled for the first time by the inclusion of sketch, all without any task-specific modifications. Project Page: \url{http://www.pinakinathc.me/scenetrilogy}

Aneeshan Sain, Ayan Kumar Bhunia, Subhadeep Koley et al.

This paper advances the fine-grained sketch-based image retrieval (FG-SBIR) literature by putting forward a strong baseline that overshoots prior state-of-the-arts by ~11%. This is not via complicated design though, but by addressing two critical issues facing the community (i) the gold standard triplet loss does not enforce holistic latent space geometry, and (ii) there are never enough sketches to train a high accuracy model. For the former, we propose a simple modification to the standard triplet loss, that explicitly enforces separation amongst photos/sketch instances. For the latter, we put forward a novel knowledge distillation module can leverage photo data for model training. Both modules are then plugged into a novel plug-n-playable training paradigm that allows for more stable training. More specifically, for (i) we employ an intra-modal triplet loss amongst sketches to bring sketches of the same instance closer from others, and one more amongst photos to push away different photo instances while bringing closer a structurally augmented version of the same photo (offering a gain of ~4-6%). To tackle (ii), we first pre-train a teacher on the large set of unlabelled photos over the aforementioned intra-modal photo triplet loss. Then we distill the contextual similarity present amongst the instances in the teacher's embedding space to that in the student's embedding space, by matching the distribution over inter-feature distances of respective samples in both embedding spaces (delivering a further gain of ~4-5%). Apart from outperforming prior arts significantly, our model also yields satisfactory results on generalising to new classes. Project page: https://aneeshan95.github.io/Sketch_PVT/

Ayan Kumar Bhunia, Subhadeep Koley, Amandeep Kumar et al.

Human sketch has already proved its worth in various visual understanding tasks (e.g., retrieval, segmentation, image-captioning, etc). In this paper, we reveal a new trait of sketches - that they are also salient. This is intuitive as sketching is a natural attentive process at its core. More specifically, we aim to study how sketches can be used as a weak label to detect salient objects present in an image. To this end, we propose a novel method that emphasises on how "salient object" could be explained by hand-drawn sketches. To accomplish this, we introduce a photo-to-sketch generation model that aims to generate sequential sketch coordinates corresponding to a given visual photo through a 2D attention mechanism. Attention maps accumulated across the time steps give rise to salient regions in the process. Extensive quantitative and qualitative experiments prove our hypothesis and delineate how our sketch-based saliency detection model gives a competitive performance compared to the state-of-the-art.

Ayan Kumar Bhunia, Aneeshan Sain, Parth Shah et al.

The recent focus on Fine-Grained Sketch-Based Image Retrieval (FG-SBIR) has shifted towards generalising a model to new categories without any training data from them. In real-world applications, however, a trained FG-SBIR model is often applied to both new categories and different human sketchers, i.e., different drawing styles. Although this complicates the generalisation problem, fortunately, a handful of examples are typically available, enabling the model to adapt to the new category/style. In this paper, we offer a novel perspective -- instead of asking for a model that generalises, we advocate for one that quickly adapts, with just very few samples during testing (in a few-shot manner). To solve this new problem, we introduce a novel model-agnostic meta-learning (MAML) based framework with several key modifications: (1) As a retrieval task with a margin-based contrastive loss, we simplify the MAML training in the inner loop to make it more stable and tractable. (2) The margin in our contrastive loss is also meta-learned with the rest of the model. (3) Three additional regularisation losses are introduced in the outer loop, to make the meta-learned FG-SBIR model more effective for category/style adaptation. Extensive experiments on public datasets suggest a large gain over generalisation and zero-shot based approaches, and a few strong few-shot baselines.

Aneeshan Sain, Pinaki Nath Chowdhury, Subhadeep Koley et al.

In this paper, we delve into the intricate dynamics of Fine-Grained Sketch-Based Image Retrieval (FG-SBIR) by addressing a critical yet overlooked aspect -- the choice of viewpoint during sketch creation. Unlike photo systems that seamlessly handle diverse views through extensive datasets, sketch systems, with limited data collected from fixed perspectives, face challenges. Our pilot study, employing a pre-trained FG-SBIR model, highlights the system's struggle when query-sketches differ in viewpoint from target instances. Interestingly, a questionnaire however shows users desire autonomy, with a significant percentage favouring view-specific retrieval. To reconcile this, we advocate for a view-aware system, seamlessly accommodating both view-agnostic and view-specific tasks. Overcoming dataset limitations, our first contribution leverages multi-view 2D projections of 3D objects, instilling cross-modal view awareness. The second contribution introduces a customisable cross-modal feature through disentanglement, allowing effortless mode switching. Extensive experiments on standard datasets validate the effectiveness of our method.

Pranay Mukherjee, Abhirup Das, Ayan Kumar Bhunia et al.

Can we ask computers to recognize what we see from brain signals alone? Our paper seeks to utilize the knowledge learnt in the visual domain by popular pre-trained vision models and use it to teach a recurrent model being trained on brain signals to learn a discriminative manifold of the human brain's cognition of different visual object categories in response to perceived visual cues. For this we make use of brain EEG signals triggered from visual stimuli like images and leverage the natural synchronization between images and their corresponding brain signals to learn a novel representation of the cognitive feature space. The concept of knowledge distillation has been used here for training the deep cognition model, CogniNet\footnote{The source code of the proposed system is publicly available at {https://www.github.com/53X/CogniNET}}, by employing a student-teacher learning technique in order to bridge the process of inter-modal knowledge transfer. The proposed novel architecture obtains state-of-the-art results, significantly surpassing other existing models. The experiments performed by us also suggest that if visual stimuli information like brain EEG signals can be gathered on a large scale, then that would help to obtain a better understanding of the largely unexplored domain of human brain cognition.

Subhadeep Koley, Ayan Kumar Bhunia, Deeptanshu Sekhri et al.

This paper unravels the potential of sketches for diffusion models, addressing the deceptive promise of direct sketch control in generative AI. We importantly democratise the process, enabling amateur sketches to generate precise images, living up to the commitment of "what you sketch is what you get". A pilot study underscores the necessity, revealing that deformities in existing models stem from spatial-conditioning. To rectify this, we propose an abstraction-aware framework, utilising a sketch adapter, adaptive time-step sampling, and discriminative guidance from a pre-trained fine-grained sketch-based image retrieval model, working synergistically to reinforce fine-grained sketch-photo association. Our approach operates seamlessly during inference without the need for textual prompts; a simple, rough sketch akin to what you and I can create suffices! We welcome everyone to examine results presented in the paper and its supplementary. Contributions include democratising sketch control, introducing an abstraction-aware framework, and leveraging discriminative guidance, validated through extensive experiments.

Hmrishav Bandyopadhyay, Subhadeep Koley, Ayan Das et al.

In this paper, we democratise 3D content creation, enabling precise generation of 3D shapes from abstract sketches while overcoming limitations tied to drawing skills. We introduce a novel part-level modelling and alignment framework that facilitates abstraction modelling and cross-modal correspondence. Leveraging the same part-level decoder, our approach seamlessly extends to sketch modelling by establishing correspondence between CLIPasso edgemaps and projected 3D part regions, eliminating the need for a dataset pairing human sketches and 3D shapes. Additionally, our method introduces a seamless in-position editing process as a byproduct of cross-modal part-aligned modelling. Operating in a low-dimensional implicit space, our approach significantly reduces computational demands and processing time.

Subhadeep Koley, Ayan Kumar Bhunia, Aneeshan Sain et al.

Two primary input modalities prevail in image retrieval: sketch and text. While text is widely used for inter-category retrieval tasks, sketches have been established as the sole preferred modality for fine-grained image retrieval due to their ability to capture intricate visual details. In this paper, we question the reliance on sketches alone for fine-grained image retrieval by simultaneously exploring the fine-grained representation capabilities of both sketch and text, orchestrating a duet between the two. The end result enables precise retrievals previously unattainable, allowing users to pose ever-finer queries and incorporate attributes like colour and contextual cues from text. For this purpose, we introduce a novel compositionality framework, effectively combining sketches and text using pre-trained CLIP models, while eliminating the need for extensive fine-grained textual descriptions. Last but not least, our system extends to novel applications in composed image retrieval, domain attribute transfer, and fine-grained generation, providing solutions for various real-world scenarios.

Subhadeep Koley, Ayan Kumar Bhunia, Aneeshan Sain et al.

This paper, for the first time, explores text-to-image diffusion models for Zero-Shot Sketch-based Image Retrieval (ZS-SBIR). We highlight a pivotal discovery: the capacity of text-to-image diffusion models to seamlessly bridge the gap between sketches and photos. This proficiency is underpinned by their robust cross-modal capabilities and shape bias, findings that are substantiated through our pilot studies. In order to harness pre-trained diffusion models effectively, we introduce a straightforward yet powerful strategy focused on two key aspects: selecting optimal feature layers and utilising visual and textual prompts. For the former, we identify which layers are most enriched with information and are best suited for the specific retrieval requirements (category-level or fine-grained). Then we employ visual and textual prompts to guide the model's feature extraction process, enabling it to generate more discriminative and contextually relevant cross-modal representations. Extensive experiments on several benchmark datasets validate significant performance improvements.

Subhadeep Koley, Ayan Kumar Bhunia, Aneeshan Sain et al.

In this paper, we propose a novel abstraction-aware sketch-based image retrieval framework capable of handling sketch abstraction at varied levels. Prior works had mainly focused on tackling sub-factors such as drawing style and order, we instead attempt to model abstraction as a whole, and propose feature-level and retrieval granularity-level designs so that the system builds into its DNA the necessary means to interpret abstraction. On learning abstraction-aware features, we for the first-time harness the rich semantic embedding of pre-trained StyleGAN model, together with a novel abstraction-level mapper that deciphers the level of abstraction and dynamically selects appropriate dimensions in the feature matrix correspondingly, to construct a feature matrix embedding that can be freely traversed to accommodate different levels of abstraction. For granularity-level abstraction understanding, we dictate that the retrieval model should not treat all abstraction-levels equally and introduce a differentiable surrogate Acc.@q loss to inject that understanding into the system. Different to the gold-standard triplet loss, our Acc.@q loss uniquely allows a sketch to narrow/broaden its focus in terms of how stringent the evaluation should be - the more abstract a sketch, the less stringent (higher q). Extensive experiments depict our method to outperform existing state-of-the-arts in standard SBIR tasks along with challenging scenarios like early retrieval, forensic sketch-photo matching, and style-invariant retrieval.

Dar-Yen Chen, Ayan Kumar Bhunia, Subhadeep Koley et al.

In this paper, we democratise caricature generation, empowering individuals to effortlessly craft personalised caricatures with just a photo and a conceptual sketch. Our objective is to strike a delicate balance between abstraction and identity, while preserving the creativity and subjectivity inherent in a sketch. To achieve this, we present Explicit Rank-1 Model Editing alongside single-image personalisation, selectively applying nuanced edits to cross-attention layers for a seamless merge of identity and style. Additionally, we propose Random Mask Reconstruction to enhance robustness, directing the model to focus on distinctive identity and style features. Crucially, our aim is not to replace artists but to eliminate accessibility barriers, allowing enthusiasts to engage in the artistry.

Aneeshan Sain, Subhajit Maity, Pinaki Nath Chowdhury et al.

As sketch research has collectively matured over time, its adaptation for at-mass commercialisation emerges on the immediate horizon. Despite an already mature research endeavour for photos, there is no research on the efficient inference specifically designed for sketch data. In this paper, we first demonstrate existing state-of-the-art efficient light-weight models designed for photos do not work on sketches. We then propose two sketch-specific components which work in a plug-n-play manner on any photo efficient network to adapt them to work on sketch data. We specifically chose fine-grained sketch-based image retrieval (FG-SBIR) as a demonstrator as the most recognised sketch problem with immediate commercial value. Technically speaking, we first propose a cross-modal knowledge distillation network to transfer existing photo efficient networks to be compatible with sketch, which brings down number of FLOPs and model parameters by 97.96% percent and 84.89% respectively. We then exploit the abstract trait of sketch to introduce a RL-based canvas selector that dynamically adjusts to the abstraction level which further cuts down number of FLOPs by two thirds. The end result is an overall reduction of 99.37% of FLOPs (from 40.18G to 0.254G) when compared with a full network, while retaining the accuracy (33.03% vs 32.77%) -- finally making an efficient network for the sparse sketch data that exhibit even fewer FLOPs than the best photo counterpart.

Subhadeep Koley, Viswanatha Reddy Gajjala, Aneeshan Sain et al.

We introduce SketchYourSeg, a novel framework that establishes freehand sketches as a powerful query modality for subjective image segmentation across entire galleries through a single exemplar sketch. Unlike text prompts that struggle with spatial specificity or interactive methods confined to single-image operations, sketches naturally combine semantic intent with structural precision. This unique dual encoding enables precise visual disambiguation for segmentation tasks where text descriptions would be cumbersome or ambiguous -- such as distinguishing between visually similar instances, specifying exact part boundaries, or indicating spatial relationships in composed concepts. Our approach addresses three fundamental challenges: (i) eliminating the need for pixel-perfect annotation masks during training with a mask-free framework; (ii) creating a synergistic relationship between sketch-based image retrieval (SBIR) models and foundation models (CLIP/DINOv2) where the former provides training signals while the latter generates masks; and (iii) enabling multi-granular segmentation capabilities through purpose-made sketch augmentation strategies. Our extensive evaluations demonstrate superior performance over existing approaches across diverse benchmarks, establishing a new paradigm for user-guided image segmentation that balances precision with efficiency.

Chaitat Utintu, Pinaki Nath Chowdhury, Aneeshan Sain et al.

Video colour editing is a crucial task for content creation, yet existing solutions either require painstaking frame-by-frame manipulation or produce unrealistic results with temporal artefacts. We present a practical, training-free framework that makes precise video colour editing accessible through an intuitive interface while maintaining professional-quality output. Our key insight is that by decoupling spatial and temporal aspects of colour editing, we can better align with users' natural workflow -- allowing them to focus on precise colour selection in key frames before automatically propagating changes across time. We achieve this through a novel technical framework that combines: (i) a simple point-and-click interface merging grid-based colour selection with automatic instance segmentation for precise spatial control, (ii) bidirectional colour propagation that leverages inherent video motion patterns, and (iii) motion-aware blending that ensures smooth transitions even with complex object movements. Through extensive evaluation on diverse scenarios, we demonstrate that our approach matches or exceeds state-of-the-art methods while eliminating the need for training or specialized hardware, making professional-quality video colour editing accessible to everyone.

Ayan Kumar Bhunia, Aneeshan Sain, Pinaki Nath Chowdhury et al.

Text recognition remains a fundamental and extensively researched topic in computer vision, largely owing to its wide array of commercial applications. The challenging nature of the very problem however dictated a fragmentation of research efforts: Scene Text Recognition (STR) that deals with text in everyday scenes, and Handwriting Text Recognition (HTR) that tackles hand-written text. In this paper, for the first time, we argue for their unification -- we aim for a single model that can compete favourably with two separate state-of-the-art STR and HTR models. We first show that cross-utilisation of STR and HTR models trigger significant performance drops due to differences in their inherent challenges. We then tackle their union by introducing a knowledge distillation (KD) based framework. This is however non-trivial, largely due to the variable-length and sequential nature of text sequences, which renders off-the-shelf KD techniques that mostly works with global fixed-length data inadequate. For that, we propose three distillation losses all of which are specifically designed to cope with the aforementioned unique characteristics of text recognition. Empirical evidence suggests that our proposed unified model performs on par with individual models, even surpassing them in certain cases. Ablative studies demonstrate that naive baselines such as a two-stage framework, and domain adaption/generalisation alternatives do not work as well, further verifying the appropriateness of our design.

Ayan Kumar Bhunia, Pinaki Nath Chowdhury, Aneeshan Sain et al.

Visual text recognition is undoubtedly one of the most extensively researched topics in computer vision. Great progress have been made to date, with the latest models starting to focus on the more practical "in-the-wild" setting. However, a salient problem still hinders practical deployment -- prior arts mostly struggle with recognising unseen (or rarely seen) character sequences. In this paper, we put forward a novel framework to specifically tackle this "unseen" problem. Our framework is iterative in nature, in that it utilises predicted knowledge of character sequences from a previous iteration, to augment the main network in improving the next prediction. Key to our success is a unique cross-modal variational autoencoder to act as a feedback module, which is trained with the presence of textual error distribution data. This module importantly translate a discrete predicted character space, to a continuous affine transformation parameter space used to condition the visual feature map at next iteration. Experiments on common datasets have shown competitive performance over state-of-the-arts under the conventional setting. Most importantly, under the new disjoint setup where train-test labels are mutually exclusive, ours offers the best performance thus showcasing the capability of generalising onto unseen words.

Ayan Kumar Bhunia, Shuvozit Ghose, Amandeep Kumar et al.

Handwritten Text Recognition (HTR) remains a challenging problem to date, largely due to the varying writing styles that exist amongst us. Prior works however generally operate with the assumption that there is a limited number of styles, most of which have already been captured by existing datasets. In this paper, we take a completely different perspective -- we work on the assumption that there is always a new style that is drastically different, and that we will only have very limited data during testing to perform adaptation. This results in a commercially viable solution -- the model has the best shot at adaptation being exposed to the new style, and the few samples nature makes it practical to implement. We achieve this via a novel meta-learning framework which exploits additional new-writer data through a support set, and outputs a writer-adapted model via single gradient step update, all during inference. We discover and leverage on the important insight that there exists few key characters per writer that exhibit relatively larger style discrepancies. For that, we additionally propose to meta-learn instance specific weights for a character-wise cross-entropy loss, which is specifically designed to work with the sequential nature of text data. Our writer-adaptive MetaHTR framework can be easily implemented on the top of most state-of-the-art HTR models. Experiments show an average performance gain of 5-7% can be obtained by observing very few new style data. We further demonstrate via a set of ablative studies the advantage of our meta design when compared with alternative adaption mechanisms.

Aneeshan Sain, Ayan Kumar Bhunia, Yongxin Yang et al.

Sketch-based image retrieval (SBIR) is a cross-modal matching problem which is typically solved by learning a joint embedding space where the semantic content shared between photo and sketch modalities are preserved. However, a fundamental challenge in SBIR has been largely ignored so far, that is, sketches are drawn by humans and considerable style variations exist amongst different users. An effective SBIR model needs to explicitly account for this style diversity, crucially, to generalise to unseen user styles. To this end, a novel style-agnostic SBIR model is proposed. Different from existing models, a cross-modal variational autoencoder (VAE) is employed to explicitly disentangle each sketch into a semantic content part shared with the corresponding photo, and a style part unique to the sketcher. Importantly, to make our model dynamically adaptable to any unseen user styles, we propose to meta-train our cross-modal VAE by adding two style-adaptive components: a set of feature transformation layers to its encoder and a regulariser to the disentangled semantic content latent code. With this meta-learning framework, our model can not only disentangle the cross-modal shared semantic content for SBIR, but can adapt the disentanglement to any unseen user style as well, making the SBIR model truly style-agnostic. Extensive experiments show that our style-agnostic model yields state-of-the-art performance for both category-level and instance-level SBIR.

Ayan Kumar Bhunia, Pinaki Nath Chowdhury, Yongxin Yang et al.

Self-supervised learning has gained prominence due to its efficacy at learning powerful representations from unlabelled data that achieve excellent performance on many challenging downstream tasks. However supervision-free pre-text tasks are challenging to design and usually modality specific. Although there is a rich literature of self-supervised methods for either spatial (such as images) or temporal data (sound or text) modalities, a common pre-text task that benefits both modalities is largely missing. In this paper, we are interested in defining a self-supervised pre-text task for sketches and handwriting data. This data is uniquely characterised by its existence in dual modalities of rasterized images and vector coordinate sequences. We address and exploit this dual representation by proposing two novel cross-modal translation pre-text tasks for self-supervised feature learning: Vectorization and Rasterization. Vectorization learns to map image space to vector coordinates and rasterization maps vector coordinates to image space. We show that the our learned encoder modules benefit both raster-based and vector-based downstream approaches to analysing hand-drawn data. Empirical evidence shows that our novel pre-text tasks surpass existing single and multi-modal self-supervision methods.

Sauradip Nag, Ayan Kumar Bhunia, Aishik Konwer et al.

Facial micro-expressions are sudden involuntary minute muscle movements which reveal true emotions that people try to conceal. Spotting a micro-expression and recognizing it is a major challenge owing to its short duration and intensity. Many works pursued traditional and deep learning based approaches to solve this issue but compromised on learning low-level features and higher accuracy due to unavailability of datasets. This motivated us to propose a novel joint architecture of spatial and temporal network which extracts time-contrasted features from the feature maps to contrast out micro-expression from rapid muscle movements. The usage of time contrasted features greatly improved the spotting of micro-expression from inconspicuous facial movements. Also, we include a memory module to predict the class and intensity of the micro-expression across the temporal frames of the micro-expression clip. Our method achieves superior performance in comparison to other conventional approaches on CASMEII dataset.

Ayan Kumar Bhunia, Abhirup Das, Ankan Kumar Bhunia et al.

Handwritten Word Recognition and Spotting is a challenging field dealing with handwritten text possessing irregular and complex shapes. The design of deep neural network models makes it necessary to extend training datasets in order to introduce variations and increase the number of samples; word-retrieval is therefore very difficult in low-resource scripts. Much of the existing literature comprises preprocessing strategies which are seldom sufficient to cover all possible variations. We propose the Adversarial Feature Deformation Module (AFDM) that learns ways to elastically warp extracted features in a scalable manner. The AFDM is inserted between intermediate layers and trained alternatively with the original framework, boosting its capability to better learn highly informative features rather than trivial ones. We test our meta-framework, which is built on top of popular word-spotting and word-recognition frameworks and enhanced by the AFDM, not only on extensive Latin word datasets but also sparser Indic scripts. We record results for varying training data sizes, and observe that our enhanced network generalizes much better in the low-data regime; the overall word-error rates and mAP scores are observed to improve as well.

Ayan Kumar Bhunia, Ankan Kumar Bhunia, Shuvozit Ghose et al.

Logo detection in real-world scene images is an important problem with applications in advertisement and marketing. Existing general-purpose object detection methods require large training data with annotations for every logo class. These methods do not satisfy the incremental demand of logo classes necessary for practical deployment since it is practically impossible to have such annotated data for new unseen logo. In this work, we develop an easy-to-implement query-based logo detection and localization system by employing a one-shot learning technique. Given an image of a query logo, our model searches for it within a given target image and predicts the possible location of the logo by estimating a binary segmentation mask. The proposed model consists of a conditional branch and a segmentation branch. The former gives a conditional latent representation of the given query logo which is combined with feature maps of the segmentation branch at multiple scales in order to find the matching position of the query logo in a target image, should it be present. Feature matching between the latent query representation and multi-scale feature maps of segmentation branch using simple concatenation operation followed by 1x1 convolution layer makes our model scale-invariant. Despite its simplicity, our query-based logo retrieval framework achieved superior performance in FlickrLogos-32 and TopLogos-10 dataset over different existing baselines.

Perla Sai Raj Kishore, Ayan Kumar Bhunia, Shuvozit Ghose et al.

Thumbnails are widely used all over the world as a preview for digital images. In this work we propose a deep neural framework to generate thumbnails of any size and aspect ratio, even for unseen values during training, with high accuracy and precision. We use Global Context Aggregation (GCA) and a modified Region Proposal Network (RPN) with adaptive convolutions to generate thumbnails in real time. GCA is used to selectively attend and aggregate the global context information from the entire image while the RPN is used to predict candidate bounding boxes for the thumbnail image. Adaptive convolution eliminates the problem of generating thumbnails of various aspect ratios by using filter weights dynamically generated from the aspect ratio information. The experimental results indicate the superior performance of the proposed model over existing state-of-the-art techniques.

Ankan Kumar Bhunia, Ayan Kumar Bhunia, Aneeshan Sain et al.

Binarization of degraded document images is an elementary step in most of the problems in document image analysis domain. The paper re-visits the binarization problem by introducing an adversarial learning approach. We construct a Texture Augmentation Network that transfers the texture element of a degraded reference document image to a clean binary image. In this way, the network creates multiple versions of the same textual content with various noisy textures, thus enlarging the available document binarization datasets. At last, the newly generated images are passed through a Binarization network to get back the clean version. By jointly training the two networks we can increase the adversarial robustness of our system. Also, it is noteworthy that our model can learn from unpaired data. Experimental results suggest that the proposed method achieves superior performance over widely used DIBCO datasets.

Ayan Kumar Bhunia, Subham Mukherjee, Aneeshan Sain et al.

In this paper, we propose a novel approach of word-level Indic script identification using only character-level data in training stage. The advantages of using character level data for training have been outlined in section I. Our method uses a multimodal deep network which takes both offline and online modality of the data as input in order to explore the information from both the modalities jointly for script identification task. We take handwritten data in either modality as input and the opposite modality is generated through intermodality conversion. Thereafter, we feed this offline-online modality pair to our network. Hence, along with the advantage of utilizing information from both the modalities, it can work as a single framework for both offline and online script identification simultaneously which alleviates the need for designing two separate script identification modules for individual modality. One more major contribution is that we propose a novel conditional multimodal fusion scheme to combine the information from offline and online modality which takes into account the real origin of the data being fed to our network and thus it combines adaptively. An exhaustive experiment has been done on a data set consisting of English and six Indic scripts. Our proposed framework clearly outperforms different frameworks based on traditional classifiers along with handcrafted features and deep learning based methods with a clear margin. Extensive experiments show that using only character level training data can achieve state-of-art performance similar to that obtained with traditional training using word level data in our framework.

Ayan Kumar Bhunia, Abir Bhowmick, Ankan Kumar Bhunia et al.

In this paper, we introduce a novel technique to recover the pen trajectory of offline characters which is a crucial step for handwritten character recognition. Generally, online acquisition approach has more advantage than its offline counterpart as the online technique keeps track of the pen movement. Hence, pen tip trajectory retrieval from offline text can bridge the gap between online and offline methods. Our proposed framework employs sequence to sequence model which consists of an encoder-decoder LSTM module. Our encoder module consists of Convolutional LSTM network, which takes an offline character image as the input and encodes the feature sequence to a hidden representation. The output of the encoder is fed to a decoder LSTM and we get the successive coordinate points from every time step of the decoder LSTM. Although the sequence to sequence model is a popular paradigm in various computer vision and language translation tasks, the main contribution of our work lies in designing an end-to-end network for a decade old popular problem in Document Image Analysis community. Tamil, Telugu and Devanagari characters of LIPI Toolkit dataset are used for our experiments. Our proposed method has achieved superior performance compared to the other conventional approaches.

Ankan Kumar Bhunia, Ayan Kumar Bhunia, Prithaj Banerjee et al.

Conversion of one font to another font is very useful in real life applications. In this paper, we propose a Convolutional Recurrent Generative model to solve the word level font transfer problem. Our network is able to convert the font style of any printed text images from its current font to the required font. The network is trained end-to-end for the complete word images. Thus it eliminates the necessary pre-processing steps, like character segmentations. We extend our model to conditional setting that helps to learn one-to-many mapping function. We employ a novel convolutional recurrent model architecture in the Generator that efficiently deals with the word images of arbitrary width. It also helps to maintain the consistency of the final images after concatenating the generated image patches of target font. Besides, the Generator and the Discriminator network, we employ a Classification network to classify the generated word images of converted font style to their subsequent font categories. Most of the earlier works related to image translation are performed on square images. Our proposed architecture is the first work which can handle images of varying widths. Word images generally have varying width depending on the number of characters present. Hence, we test our model on a synthetically generated font dataset. We compare our method with some of the state-of-the-art methods for image translation. The superior performance of our network on the same dataset proves the ability of our model to learn the font distributions.

Aishik Konwer, Ayan Kumar Bhunia, Abir Bhowmick et al.

Staff line removal is a crucial pre-processing step in Optical Music Recognition. It is a challenging task to simultaneously reduce the noise and also retain the quality of music symbol context in ancient degraded music score images. In this paper we propose a novel approach for staff line removal, based on Generative Adversarial Networks. We convert staff line images into patches and feed them into a U-Net, used as Generator. The Generator intends to produce staff-less images at the output. Then the Discriminator does binary classification and differentiates between the generated fake staff-less image and real ground truth staff less image. For training, we use a Loss function which is a weighted combination of L2 loss and Adversarial loss. L2 loss minimizes the difference between real and fake staff-less image. Adversarial loss helps to retrieve more high quality textures in generated images. Thus our architecture supports solutions which are closer to ground truth and it reflects in our results. For evaluation we consider the ICDAR/GREC 2013 staff removal database. Our method achieves superior performance in comparison to other conventional approaches.

Ayan Kumar Bhunia, Avirup Bhattacharyya, Prithaj Banerjee et al.

In this paper, we have proposed a novel feature descriptors combining color and texture information collectively. In our proposed color descriptor component, the inter-channel relationship between Hue (H) and Saturation (S) channels in the HSV color space has been explored which was not done earlier. We have quantized the H channel into a number of bins and performed the voting with saturation values and vice versa by following a principle similar to that of the HOG descriptor, where orientation of the gradient is quantized into a certain number of bins and voting is done with gradient magnitude. This helps us to study the nature of variation of saturation with variation in Hue and nature of variation of Hue with the variation in saturation. The texture component of our descriptor considers the co-occurrence relationship between the pixels symmetric about both the diagonals of a 3x3 window. Our work is inspired from the work done by Dubey et al.[1]. These two components, viz. color and texture information individually perform better than existing texture and color descriptors. Moreover, when concatenated the proposed descriptors provide significant improvement over existing descriptors for content base color image retrieval. The proposed descriptor has been tested for image retrieval on five databases, including texture image databases - MIT VisTex database and Salzburg texture database and natural scene databases Corel 1K, Corel 5K and Corel 10K. The precision and recall values experimented on these databases are compared with some state-of-art local patterns. The proposed method provided satisfactory results from the experiments.

Ankan Kumar Bhunia, Aishik Konwer, Ayan Kumar Bhunia et al.

Script identification plays a significant role in analysing documents and videos. In this paper, we focus on the problem of script identification in scene text images and video scripts. Because of low image quality, complex background and similar layout of characters shared by some scripts like Greek, Latin, etc., text recognition in those cases become challenging. In this paper, we propose a novel method that involves extraction of local and global features using CNN-LSTM framework and weighting them dynamically for script identification. First, we convert the images into patches and feed them into a CNN-LSTM framework. Attention-based patch weights are calculated applying softmax layer after LSTM. Next, we do patch-wise multiplication of these weights with corresponding CNN to yield local features. Global features are also extracted from last cell state of LSTM. We employ a fusion technique which dynamically weights the local and global features for an individual patch. Experiments have been done in four public script identification datasets: SIW-13, CVSI2015, ICDAR-17 and MLe2e. The proposed framework achieves superior results in comparison to conventional methods.

Shuvozit Ghose, Abhirup Das, Ayan Kumar Bhunia et al.

In this paper, a new texture descriptor named "Fractional Local Neighborhood Intensity Pattern" (FLNIP) has been proposed for content based image retrieval (CBIR). It is an extension of the Local Neighborhood Intensity Pattern (LNIP)[1]. FLNIP calculates the relative intensity difference between a particular pixel and the center pixel of a 3x3 window by considering the relationship with adjacent neighbors. In this work, the fractional change in the local neighborhood involving the adjacent neighbors has been calculated first with respect to one of the eight neighbors of the center pixel of a 3x3 window. Next, the fractional change has been calculated with respect to the center itself. The two values of fractional change are next compared to generate a binary bit pattern. Both sign and magnitude information are encoded in a single descriptor as it deals with the relative change in magnitude in the adjacent neighborhood i.e., the comparison of the fractional change. The descriptor is applied on four multi-resolution images -- one being the raw image and the other three being filtered gaussian images obtained by applying gaussian filters of different standard deviations on the raw image to signify the importance of exploring texture information at different resolutions in an image. The four sets of distances obtained between the query and the target image are then combined with a genetic algorithm based approach to improve the retrieval performance by minimizing the distance between similar class images. The performance of the method has been tested for image retrieval on four popular databases. The precision and recall values observed on these databases have been compared with recent state-of-art local patterns. The proposed method has shown a significant improvement over many other existing methods.

Ayan Kumar Bhunia, Partha Pratim Roy, Akash Mohta et al.

Handwritten word recognition and spotting of low-resource scripts are difficult as sufficient training data is not available and it is often expensive for collecting data of such scripts. This paper presents a novel cross language platform for handwritten word recognition and spotting for such low-resource scripts where training is performed with a sufficiently large dataset of an available script (considered as source script) and testing is done on other scripts (considered as target script). Training with one source script and testing with another script to have a reasonable result is not easy in handwriting domain due to the complex nature of handwriting variability among scripts. Also it is difficult in mapping between source and target characters when they appear in cursive word images. The proposed Indic cross language framework exploits a large resource of dataset for training and uses it for recognizing and spotting text of other target scripts where sufficient amount of training data is not available. Since, Indic scripts are mostly written in 3 zones, namely, upper, middle and lower, we employ zone-wise character (or component) mapping for efficient learning purpose. The performance of our cross-language framework depends on the extent of similarity between the source and target scripts. Hence, we devise an entropy based script similarity score using source to target character mapping that will provide a feasibility of cross language transcription. We have tested our approach in three Indic scripts, namely, Bangla, Devanagari and Gurumukhi, and the corresponding results are reported.

Ayan Kumar Bhunia, Partha Pratim Roy, Umapada Pal

In this paper we present a word spotting system in text lines for offline Indic scripts such as Bangla (Bengali) and Devanagari. Recently, it was shown that zone-wise recognition method improves the word recognition performance than conventional full word recognition system in Indic scripts. Inspired with this idea we consider the zone segmentation approach and use middle zone information to improve the traditional word spotting performance. To avoid the problem of zone segmentation using heuristic approach, we propose here an HMM based approach to segment the upper and lower zone components from the text line images. The candidate keywords are searched from a line without segmenting characters or words. Also, we propose a novel feature combining foreground and background information of text line images for keyword-spotting by character filler models. A significant improvement in performance is noted by using both foreground and background information than their individual one. Pyramid Histogram of Oriented Gradient (PHOG) feature has been used in our word spotting framework. From the experiment, it has been noted that the proposed zone-segmentation based system outperforms traditional approaches of word spotting.

Prithaj Banerjee, Ayan Kumar Bhunia, Avirup Bhattacharyya et al.

In this paper, a new texture descriptor based on the local neighborhood intensity difference is proposed for content based image retrieval (CBIR). For computation of texture features like Local Binary Pattern (LBP), the center pixel in a 3*3 window of an image is compared with all the remaining neighbors, one pixel at a time to generate a binary bit pattern. It ignores the effect of the adjacent neighbors of a particular pixel for its binary encoding and also for texture description. The proposed method is based on the concept that neighbors of a particular pixel hold a significant amount of texture information that can be considered for efficient texture representation for CBIR. Taking this into account, we develop a new texture descriptor, named as Local Neighborhood Intensity Pattern (LNIP) which considers the relative intensity difference between a particular pixel and the center pixel by considering its adjacent neighbors and generate a sign and a magnitude pattern. Since sign and magnitude patterns hold complementary information to each other, these two patterns are concatenated into a single feature descriptor to generate a more concrete and useful feature descriptor. The proposed descriptor has been tested for image retrieval on four databases, including three texture image databases - Brodatz texture image database, MIT VisTex database and Salzburg texture database and one face database AT&T face database. The precision and recall values observed on these databases are compared with some state-of-art local patterns. The proposed method showed a significant improvement over many other existing methods.

Partha Pratim Roy, Ayan Kumar Bhunia, Avirup Bhattacharyya et al.

Retrieval of text information from natural scene images and video frames is a challenging task due to its inherent problems like complex character shapes, low resolution, background noise, etc. Available OCR systems often fail to retrieve such information in scene/video frames. Keyword spotting, an alternative way to retrieve information, performs efficient text searching in such scenarios. However, current word spotting techniques in scene/video images are script-specific and they are mainly developed for Latin script. This paper presents a novel word spotting framework using dynamic shape coding for text retrieval in natural scene image and video frames. The framework is designed to search query keyword from multiple scripts with the help of on-the-fly script-wise keyword generation for the corresponding script. We have used a two-stage word spotting approach using Hidden Markov Model (HMM) to detect the translated keyword in a given text line by identifying the script of the line. A novel unsupervised dynamic shape coding based scheme has been used to group similar shape characters to avoid confusion and to improve text alignment. Next, the hypotheses locations are verified to improve retrieval performance. To evaluate the proposed system for searching keyword from natural scene image and video frames, we have considered two popular Indic scripts such as Bangla (Bengali) and Devanagari along with English. Inspired by the zone-wise recognition approach in Indic scripts[1], zone-wise text information has been used to improve the traditional word spotting performance in Indic scripts. For our experiment, a dataset consisting of images of different scenes and video frames of English, Bangla and Devanagari scripts were considered. The results obtained showed the effectiveness of our proposed word spotting approach.

Partha Pratim Roy, Ayan Kumar Bhunia, Ayan Das et al.

This paper presents a novel approach towards Indic handwritten word recognition using zone-wise information. Because of complex nature due to compound characters, modifiers, overlapping and touching, etc., character segmentation and recognition is a tedious job in Indic scripts (e.g. Devanagari, Bangla, Gurumukhi, and other similar scripts). To avoid character segmentation in such scripts, HMM-based sequence modeling has been used earlier in holistic way. This paper proposes an efficient word recognition framework by segmenting the handwritten word images horizontally into three zones (upper, middle and lower) and recognize the corresponding zones. The main aim of this zone segmentation approach is to reduce the number of distinct component classes compared to the total number of classes in Indic scripts. As a result, use of this zone segmentation approach enhances the recognition performance of the system. The components in middle zone where characters are mostly touching are recognized using HMM. After the recognition of middle zone, HMM based Viterbi forced alignment is applied to mark the left and right boundaries of the characters. Next, the residue components, if any, in upper and lower zones in their respective boundary are combined to achieve the final word level recognition. Water reservoir feature has been integrated in this framework to improve the zone segmentation and character alignment defects while segmentation. A novel sliding window-based feature, called Pyramid Histogram of Oriented Gradient (PHOG) is proposed for middle zone recognition. An exhaustive experiment is performed on two Indic scripts namely, Bangla and Devanagari for the performance evaluation. From the experiment, it has been noted that proposed zone-wise recognition improves accuracy with respect to the traditional way of Indic word recognition.

Aneeshan Sain, Ayan Kumar Bhunia, Partha Pratim Roy et al.

In this paper, we bring forth a novel approach of video text detection using Fourier-Laplacian filtering in the frequency domain that includes a verification technique using Hidden Markov Model (HMM). The proposed approach deals with the text region appearing not only in horizontal or vertical directions, but also in any other oblique or curved orientation in the image. Until now only a few methods have been proposed that look into curved text detection in video frames, wherein lies our novelty. In our approach, we first apply Fourier-Laplacian transform on the image followed by an ideal Laplacian-Gaussian filtering. Thereafter K-means clustering is employed to obtain the asserted text areas depending on a maximum difference map. Next, the obtained connected components (CC) are skeletonized to distinguish various text strings. Complex components are disintegrated into simpler ones according to a junction removal algorithm followed by a concatenation performed on possible combination of the disjoint skeletons to obtain the corresponding text area. Finally these text hypotheses are verified using HMM-based text/non-text classification system. False positives are thus eliminated giving us a robust text detection performance. We have tested our framework in multi-oriented text lines in four scripts, namely, English, Chinese, Devanagari and Bengali, in video frames and scene texts. The results obtained show that proposed approach surpasses existing methods on text detection.

Partha Pratim Roy, Ayan Kumar Bhunia, Umapada Pal

Text recognition in scene image and video frames is difficult because of low resolution, blur, background noise, etc. Since traditional OCRs do not perform well in such images, information retrieval using keywords could be an alternative way to index/retrieve such text information. Date is a useful piece of information which has various applications including date-wise videos/scene searching, indexing or retrieval. This paper presents a date spotting based information retrieval system for natural scene image and video frames where text appears with complex backgrounds. We propose a line based date spotting approach using Hidden Markov Model (HMM) which is used to detect the date information in a given text. Different date models are searched from a line without segmenting characters or words. Given a text line image in RGB, we apply an efficient gray image conversion to enhance the text information. Wavelet decomposition and gradient sub-bands are used to enhance text information in gray scale. Next, Pyramid Histogram of Oriented Gradient (PHOG) feature has been extracted from gray image and binary images for date-spotting framework. Binary and gray image features are combined by MLP based Tandem approach. Finally, to boost the performance further, a shape coding based scheme is used to combine the similar shape characters in same class during word spotting. For our experiment, three different date models have been constructed to search similar date information having numeric dates that contains numeral values and punctuations and semi-numeric that contains dates with numerals along with months in scene/video text. We have tested our system on 1648 text lines and the results show the effectiveness of our proposed date spotting approach.

Partha Pratim Roy, Ayan Kumar Bhunia, Umapada Pal

Writer identification from musical score documents is a challenging task due to its inherent problem of overlapping of musical symbols with staff lines. Most of the existing works in the literature of writer identification in musical score documents were performed after a preprocessing stage of staff lines removal. In this paper we propose a novel writer identification framework in musical documents without removing staff lines from documents. In our approach, Hidden Markov Model has been used to model the writing style of the writers without removing staff lines. The sliding window features are extracted from musical score lines and they are used to build writer specific HMM models. Given a query musical sheet, writer specific confidence for each musical line is returned by each writer specific model using a loglikelihood score. Next, a loglikelihood score in page level is computed by weighted combination of these scores from the corresponding line images of the page. A novel Factor Analysis based feature selection technique is applied in sliding window features to reduce the noise appearing from staff lines which proves efficiency in writer identification performance.In our framework we have also proposed a novel score line detection approach in musical sheet using HMM. The experiment has been performed in CVC-MUSCIMA dataset and the results obtained that the proposed approach is efficient for score line detection and writer identification without removing staff lines. To get the idea of computation time of our method, detail analysis of execution time is also provided.